{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BP4763543XM37UKNN5DWKFNIJW","short_pith_number":"pith:BP476354","schema_version":"1.0","canonical_sha256":"0bf9ff6fbcddd9bfd14d6f476515a84d9bc43f7074d5d9d0ec5fbca56bd364a4","source":{"kind":"arxiv","id":"1711.01970","version":2},"attestation_state":"computed","paper":{"title":"Optimal transport maps for distribution preserving operations on latent spaces of Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Sage, Eirikur Agustsson, Luc Van Gool, Radu Timofte","submitted_at":"2017-11-06T15:51:29Z","abstract_excerpt":"Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian. After a trained model is obtained, one can sample the Generator in various forms for exploration and understanding, such as interpolating between two samples, sampling in the vicinity of a sample or exploring differences between a pair of samples applied to a third sample. In this paper, we show that the latent space operations used in the literature so far induce a distribution mismatch betw"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.01970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-06T15:51:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3371a9af052c119fcc102bd43d2a8cf0728f5f6f788ea3b99d293addb817e8fb","abstract_canon_sha256":"ed8458ef92467e8fdf6b9e2b3adff1b789210f6aca6b7562da012455502fdb4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:07.393817Z","signature_b64":"U2XbfmTr2ecWmmDWnHh3SzWKKng1lhydEXwrzLofFhbvg46npJYiwT85cPYG0u3VizDxoEnkBhpnJmq9lKvbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf9ff6fbcddd9bfd14d6f476515a84d9bc43f7074d5d9d0ec5fbca56bd364a4","last_reissued_at":"2026-05-18T00:25:07.393122Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:07.393122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal transport maps for distribution preserving operations on latent spaces of Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Sage, Eirikur Agustsson, Luc Van Gool, Radu Timofte","submitted_at":"2017-11-06T15:51:29Z","abstract_excerpt":"Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian. After a trained model is obtained, one can sample the Generator in various forms for exploration and understanding, such as interpolating between two samples, sampling in the vicinity of a sample or exploring differences between a pair of samples applied to a third sample. In this paper, we show that the latent space operations used in the literature so far induce a distribution mismatch betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01970","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.01970","created_at":"2026-05-18T00:25:07.393265+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01970v2","created_at":"2026-05-18T00:25:07.393265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01970","created_at":"2026-05-18T00:25:07.393265+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP4763543XM3","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP4763543XM37UKN","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP476354","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30821","citing_title":"Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW","json":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW.json","graph_json":"https://pith.science/api/pith-number/BP4763543XM37UKNN5DWKFNIJW/graph.json","events_json":"https://pith.science/api/pith-number/BP4763543XM37UKNN5DWKFNIJW/events.json","paper":"https://pith.science/paper/BP476354"},"agent_actions":{"view_html":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW","download_json":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW.json","view_paper":"https://pith.science/paper/BP476354","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01970&json=true","fetch_graph":"https://pith.science/api/pith-number/BP4763543XM37UKNN5DWKFNIJW/graph.json","fetch_events":"https://pith.science/api/pith-number/BP4763543XM37UKNN5DWKFNIJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW/action/storage_attestation","attest_author":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW/action/author_attestation","sign_citation":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW/action/citation_signature","submit_replication":"https://pith.science/pith/BP4763543XM37UKNN5DWKFNIJW/action/replication_record"}},"created_at":"2026-05-18T00:25:07.393265+00:00","updated_at":"2026-05-18T00:25:07.393265+00:00"}